© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48364
    Prev
    Next
    INDEX
    Explanations

    airlines and air travel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĢħ
    -0.09
     Commission
    -0.09
    æĮ¯
    -0.09
    èĮ«çĦ¶
    -0.09
    Ñħодим
    -0.09
    ä¹ĥ
    -0.08
    olon
    -0.08
    åįģå¤ļ
    -0.08
    leaning
    -0.08
    èĻij
    -0.08
    POSITIVE LOGITS
    èĤ¡ä¸ľå¤§ä¼ļ
    0.10
    æĮ¤
    0.09
     founders
    0.09
    åĪĽå§ĭ人
    0.08
    çļĦåĪ°æĿ¥
    0.08
     Vince
    0.08
    磮
    0.08
     Huntington
    0.08
     Vil
    0.08
    elles
    0.08
    Activations Density 0.022%

    No Known Activations